A modular graph-based Retrieval-Augmented Generation (RAG) system

CodeRAG is an AI-powered tool for real-time codebase querying and augmentation using OpenAI and vector search.

ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

[ACL 2024 Findings] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning https://arxiv.org/abs/2311.10537

Conversational Health Agents: A Personalized LLM-powered Agent Framework

[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

This work has been accepted to Findings of EMNLP 2025!

A Language Agent for Autonomous Driving

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

A repo lists papers related to LLM based agent

Survey on LLM Agents (Published on CoLing 2025)

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

A lightweight, powerful framework for multi-agent workflows

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"